Personalize QA System with Contextual Memory using GooglePalm

Abstract

Personalized Q&A System with Contextual memory using GooglePalm, LangChain in Ed-Tech Industry aims to build a CQA(Conversational Question Answer) system which is a interactive search systems that effectively serve information by interacting with users. Despite its effectiveness, challenges exist as human annotation is time consuming, inconsistent, and not scalable. To address this issue and investigate the applicability of large language models in conversational question-answering (CQA) simulation, we propose a simulation framework that employs Langchain, Google Palm LLMs. Here we will add a csv file which consists of frequently asked questions. Furthermore, we conduct extensive analyses to thoroughly examine the LLM performance by benchmarking state-of-the-art reading comprehension models on datasets. Our results reveal that the Service Provider LLM generates lengthier answers that tend to be more accurate and complete. This is an end to end LLM project based on Google Palm and Langchain. We are building a Q&A system for an ed-learning company. In particular, noting that it takes time for the user to speak, threading related to database searches is performed while the user is speaking.